A framework for multi-type recommendations

Collaborative filtering (CF) as an effective method of recommender systems (RS) has been widely used in online stores. However, CF suffers some weaknesses: problems with new users (cold start), data sparseness, difficulty in spotting “malicious” or “unreliable” users and so on. Additionally CF can´t recommend different type items at the same time. So in order to make it adaptive new Web applications, such as urban computing, visit schedule planning and so on, the authors introduce a new recommendation framework, which combines CF and case-based reasoning (CBR) to improve performance of RS. Based on this framework, the authors have developed a semantic search demo system-MyVisit, which shows that our proposed framework is an effective recommendation model.